Triple
T30171151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Court Square station complex |
E766922
|
entity |
| Predicate | hasAdjacentStationOnG |
P183122
|
FINISHED |
| Object | 21st Street |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 21st Street | Statement: [Court Square station complex, hasAdjacentStationOnG, 21st Street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdjacentStationOnG Context triple: [Court Square station complex, hasAdjacentStationOnG, 21st Street]
-
A.
hasAdjacentStationOnM
Indicates that one station is directly next to another station along metro line M, with no other stations in between.
-
B.
hasAdjacentStationOnL
Indicates that one station is directly next to another station along line L in the network.
-
C.
hasAdjacentStationOnAC
Indicates that one station is directly next to another station along the AC line or route.
-
D.
hasAdjacentStations
Indicates that two stations are directly next to each other in a sequence or network, with no other station in between.
-
E.
hasAdjacentStationSite
Indicates that one station site is located directly next to or bordering another station site.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f2247ba20c81909d34f2bfed706e1e |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f798387ea481909f51303f53a22e52 |
completed | May 3, 2026, 6:47 p.m. |
| PD | Predicate disambiguation | batch_69f7961550f88190b7bb8a9155458b54 |
completed | May 3, 2026, 6:38 p.m. |
| PDg | Predicate description generation | batch_69f79798663481908d6bc48dd6a94ca6 |
completed | May 3, 2026, 6:44 p.m. |
Created at: April 29, 2026, 7:24 p.m.